CN117437291B - Digital stockpile visualization method based on binocular vision - Google Patents
Digital stockpile visualization method based on binocular vision Download PDFInfo
- Publication number
- CN117437291B CN117437291B CN202311769054.XA CN202311769054A CN117437291B CN 117437291 B CN117437291 B CN 117437291B CN 202311769054 A CN202311769054 A CN 202311769054A CN 117437291 B CN117437291 B CN 117437291B
- Authority
- CN
- China
- Prior art keywords
- data
- dimensional
- scanning
- material pile
- bulk cargo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007794 visualization technique Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 31
- 239000000463 material Substances 0.000 claims abstract description 28
- 239000013590 bulk material Substances 0.000 claims abstract description 26
- 238000012800 visualization Methods 0.000 claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000011161 development Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 241000256837 Apidae Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
A digital material pile visual method based on binocular vision relates to the technical field of intelligent unloading of bulk cargo wharf, S1, a three-dimensional binocular camera is adopted to establish a bulk cargo three-dimensional scanning system; s2, bulk cargo scanning is carried out by utilizing a three-dimensional scanning system, three-dimensional data are collected, and the relative height of a bulk cargo stack is updated in real time; s3, carrying out data processing on the acquired three-dimensional data; the data processing comprises bulk three-dimensional coordinate conversion, interference data removal and regular grid DEM data processing; s4, visualizing the processed three-dimensional data; the digital material pile visualization method is introduced into a binocular vision system, and the visualization of the bulk material pile is realized by optimizing a scanning mode and data processing.
Description
Technical Field
The invention relates to the technical field of intelligent unloading of bulk cargo wharf, in particular to a binocular vision-based digital material pile visualization method.
Background
Along with the continuous development of international trade and the annual and daily increase of bulk cargo wharfs, each domestic bulk cargo wharfs are also meeting the challenge, and the comprehensive level of each bulk cargo wharfs is improved; in order to stand still in the fierce competition, the port is required to not only standardize the management flow, but also gradually change the traditional loading and unloading process mode, thereby improving the intelligent degree and the loading and unloading efficiency and reducing the labor intensity of workers; under the background, informatization, digitalization and intelligent bulk cargo wharf become hot spots for people to study and chase; the acquisition and the outline visualization of the outline data of the bulk cargo material pile are one difficult problem to be mainly overcome in the control research process of the intelligent grab ship unloader at present.
Disclosure of Invention
In order to overcome the defects in the background technology and solve the prior art, the invention discloses a digital material pile visualization method based on binocular vision, which introduces a binocular vision system and realizes the visualization of bulk material piles by optimizing a scanning mode and data processing.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
A binocular vision-based digital stockpile visualization method, comprising the following steps: s1, a three-dimensional binocular camera is adopted to establish a bulk cargo three-dimensional scanning system; s2, bulk cargo scanning is carried out by utilizing a three-dimensional scanning system, three-dimensional data are collected, and the relative height of a bulk cargo stack is updated in real time; s3, carrying out data processing on the acquired three-dimensional data; the data processing comprises bulk three-dimensional coordinate conversion, interference data removal and regular grid DEM data processing; and S4, visualizing the processed three-dimensional data.
Further, in S1, the three-dimensional binocular camera runs through the cart and the trolley of the ship unloader to complete column scanning and row scanning, the grab buckets of the three-dimensional binocular camera and the ship unloader are arranged on the trolley at intervals along the running direction of the trolley, and the cart and the trolley feedback-control the running distance through the absolute value encoder.
Further, in S2, the bulk scanning flow is: firstly moving a cart to a starting position at one side of a bulk material pile, stopping, then controlling the cart to move and simultaneously starting a binocular camera to work, scanning one row of the bulk material pile, and completing calculation of surface structure distribution of the bulk material pile below; after the trolley scans one row to return to the starting point, calculating the distance from the trolley to the next row according to the surface reconstruction condition of the bulk material pile, moving the trolley to the next row, and scanning the next row area by the moving trolley until the surface scanning reconstruction of the whole material pile is finished.
Further, in the line scanning path, the first position point of the grab bucket of the ship unloader corresponding to the blanking hopper, the second position point and the third position point of the binocular camera corresponding to the two end edges of the bulk cargo material pile, and the fourth position point and the fifth position point of the grab bucket of the ship unloader corresponding to the two end edges of the bulk cargo material pile are included.
Further, in S2, the binocular camera data acquisition is that the surface data of the bulk cargo stacker collected by the acquisition is first subjected to preliminary analysis and data reliability test, and then the verified data is subjected to data analysis according to a format of a protocol, so as to obtain binocular camera measurement data in a polar coordinate expression form.
Further, in S3, the interference data removal means to eliminate redundant data and error data.
Further, in S3, the three-dimensional coordinate transformation is to use the cart row to make the initial position as the origin of coordinates, use the cart travelling direction as the y axis, use the cart travelling direction as the x axis to establish a bulk material pile coordinate system o-xyz, set the B point coordinate as (x, y, z) under the binocular camera coordinate system, as (u, v, w) under the bulk material pile coordinate system, and the binocular camera origin as (u 0, v0, w 0) under the bulk material pile coordinate system, so as to obtain the transformation relation (u, v, w) = (x, y, z) + (u 0, v0, w 0) from the binocular camera coordinate system to the bulk material pile coordinate system; wherein u0, v0, w0 can be calculated by the positions of the cart and the trolley in the bulk material pile coordinate system; thereby converting the coordinates output by the binocular camera into three-dimensional coordinates of bulk cargo in a bulk cargo stack coordinate system.
Further, in S3, the regular grid DEM data processing includes grid normalization processing and spatial interpolation of discretized data.
Further, in S4, the visualization of the three-dimensional data includes bulk material pile surface reconstruction and three-dimensional visualization of pile data; after DEM data processing is completed, regular grid data is obtained, the regular grid is regarded as a grid image, the grid size corresponds to the pixel size of the image, and the elevation value corresponds to the gray value, so that the grid image is equivalent to the digital image; the visual component adopts VC++6.0 as a development tool under the Windows platform, adopts OpenGL to draw the dynamic change condition of the three-dimensional surface of the stockpile in real time, and simultaneously selects Direct3D under the Windows platform.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
According to the binocular vision-based digital stockpile visual method disclosed by the invention, a binocular camera is introduced to establish a bulk cargo three-dimensional scanning system, and three-dimensional coordinate data of the surface of a measured object is rapidly acquired in a large area and high resolution by a binocular vision measurement method; the binocular camera can calculate parallax between the two cameras, so that depth information of objects in a scene is obtained, and three-dimensional reconstruction and depth perception are realized;
According to the binocular vision-based digital stockpile visual method disclosed by the invention, when the grab bucket is used for taking materials and returning, the ship body height data can be scanned and updated in real time, so that the authenticity and reliability of data scanning and acquisition are greatly improved;
The invention discloses a binocular vision-based digital stockpile visual method, which comprises the steps of analyzing and error processing data acquired by binocular vision, establishing a proper coordinate system, carrying out coordinate conversion and data filtering processing, processing discrete data acquired by binocular vision by using regular grid data, converting the discrete data into regular grid data after regular grid, carrying out linear interpolation on the regular grid to form a continuous data surface, and drawing the three-dimensional surface dynamic change condition of a stockpile in real time by using OpenGL; thereby the key and difficult problems of realizing the intelligent operation of the grab ship unloader are solved, so as to realize the visualization of bulk cargo piles.
Drawings
FIG. 1 is a schematic diagram of the mounting layout of a binocular camera of the present invention;
FIG. 2 is a schematic diagram of a binocular camera scanning operating point location of the present invention;
FIG. 3 is a schematic diagram of binocular camera coordinates established by the present invention for acquiring material surface information at each location in the projection plane of the stockpile by means of a binocular camera;
FIG. 4 is an image of a material surface at a point in the camera of the present invention;
FIG. 5 is a diagram of a bulk material pile data coordinate transformation in accordance with the present invention;
FIG. 6 is a flow chart of the real-time calculation of the updated hull height at the time of the present invention;
FIG. 7 is a flow chart of an embodiment of region growing for image segmentation of the present invention.
Detailed Description
In the description, it should be understood that, if there is an azimuth or positional relationship indicated by terms such as "upper", "lower", "front", "rear", "left", "right", etc., the drawings merely correspond to the drawings of the present invention, and in order to facilitate description of the present invention, it is not indicated or implied that the device or element referred to must have a specific azimuth:
The invention discloses a binocular vision-based digital stockpile visualization method, which comprises the following steps of:
Step one, a three-dimensional binocular camera is adopted to establish a bulk cargo three-dimensional scanning system;
The binocular vision measurement technology has the outstanding advantages that three-dimensional coordinate data of the surface of a measured object can be rapidly acquired in a large area and high resolution by a binocular vision measurement method, a large amount of space point location information can be rapidly acquired, and a brand new technical means is provided for rapidly establishing a three-dimensional image model of an object; the binocular camera has the characteristics of rapidness, non-contact property, penetrability, real-time, dynamic property, initiative, high density, high precision, digitization, automation and the like, and can calculate the parallax between two cameras, so that the depth information of an object in a scene is obtained, and three-dimensional reconstruction and depth perception are realized; the binocular camera can also provide more accurate object positioning, obstacle detection, distance measurement and other functions; therefore, a main instrument for scanning bulk cargo in real time by a binocular camera is selected in the process of collecting bulk cargo three-dimensional data of the intelligent grab ship unloader; in combination with the port environment, the application selects a gray point Bumblebee series binocular camera to ensure reliability and practicability;
The scanning system specifically comprises a three-dimensional binocular camera and a grab bucket of the ship unloader, wherein the three-dimensional binocular camera is arranged on the trolley at intervals along the running direction of the trolley, and the running distance of the trolley and the trolley is controlled by an absolute value encoder in a feedback way, so that column scanning and row scanning are completed; the three-dimensional scanning system has the advantages that two scans of a stacking area can be completed in the moving process of the grab bucket without additional scanning by lengthening the main beam length of the ship unloader and fixing the distance between the grab bucket and the binocular camera; in addition, the binocular camera is not additionally provided with a motor, the binocular camera is driven by the trolley to finish scanning, the guide rail and the main beam motor are provided with high-precision absolute value encoders, the measuring precision of the high-precision absolute value encoders can reach the pulse, the requirement of a scanning process is met, and the scheme has no additional requirement on other systems.
As shown in fig. 3, the distance of the connecting line of the projection centers of the two cameras is b, which is also called a base line, any point P in the three-dimensional space is PL at the imaging point of the left camera, and PR at the imaging point of the right camera; according to the principle of linear propagation of light, the three-dimensional space point P is the intersection point of the projection center points of the two cameras and the connecting line of the imaging points; line segments L and R are the distances from the imaging points of the left camera and the right camera to the left imaging surface respectively, so that the parallax of the point P on the left camera and the right camera can be defined as XL-XR; the distance between the two imaging points PL and PR is b- (XL-L/2) - (L/2-XR), and b- (XL-XR) can be obtained after simplification; from the theory of similar triangles it can be derived that (b- (XL-XR))/(Z-f) is equal to b/Z; the distance Z of the point P to the projection center plane can be obtained.
As shown in fig. 4, the three-dimensional space point P is an imaging diagram of the camera; from the principle of similar triangles, it can be seen that (X-X0)/f=x/Z, (Y-Y0)/f=y/Z; solving the coordinate XY of the available point P; therefore, when the parallax of any point on the three-dimensional space on different images is known, the three-dimensional coordinates of the point can be known according to the parameters of the camera.
Step two, bulk cargo scanning is carried out by utilizing a three-dimensional scanning system, three-dimensional data are collected, and the relative height of a bulk cargo stack is updated in real time; the binocular data acquisition module is used for acquiring real three-dimensional data in real time, firstly, carrying out preliminary analysis and data reliability test on bulk cargo stacker surface data collected by the acquisition module, and further analyzing the verified data according to the format data of the protocol so as to acquire binocular camera measurement data in a polar coordinate expression form;
As shown in fig. 2, the bulk scanning flow is: firstly moving a cart to a starting position at one side of a bulk material pile, stopping, then controlling the cart to move and simultaneously starting a binocular camera to work, scanning one row of the bulk material pile, and completing calculation of surface structure distribution of the bulk material pile below; after a trolley scans one row to return to a starting point, calculating the distance from the trolley to the next row according to the surface reconstruction condition of the bulk material pile, moving the trolley to the next row, and scanning a next row area by the moving trolley until the surface scanning reconstruction of the whole material pile is finished; it should be noted that in the line scanning path, the first position point of the grab bucket of the ship unloader corresponding to the blanking hopper, the second position point and the third position point of the binocular camera corresponding to the edges of the two ends of the bulk material pile, and the fourth position point and the fifth position point of the grab bucket of the ship unloader corresponding to the edges of the two ends of the bulk material pile are included;
When the bulk cargo ship is fully loaded, the deck height is maintained at a comparative value, and the whole ship is continuously lifted along with continuous ship unloading work, so the deck height is data changing at any time in the ship unloading process, and the invention scans and updates the ship body height in real time when the grab bucket is used for taking materials back, and the specific flow is shown in figure 6.
Thirdly, performing data processing on the acquired three-dimensional data; the data processing comprises bulk three-dimensional coordinate conversion, interference data removal and regular grid DEM data processing;
The three-dimensional coordinate conversion is to use a cart to enable an initial position to be a coordinate origin, use a cart travelling direction to be a y axis, use a cart travelling direction to be an x axis to establish a bulk cargo material pile coordinate system o-xyz, set a B point coordinate to be (x, y, z) under a binocular camera coordinate system, be (u, v, w) under the bulk cargo material pile coordinate system, and set the binocular camera origin to be (u 0, v0, w 0) under the bulk cargo material pile coordinate system, so that a conversion relation (u, v, w) between the binocular camera coordinate system and the bulk cargo material pile coordinate system can be obtained; wherein u0, v0, w0 can be calculated by the positions of the cart and the trolley in the bulk material pile coordinate system; thereby converting the coordinates output by the binocular camera into three-dimensional coordinates of bulk cargo under a bulk cargo material pile coordinate system;
The interference data removal means that the data density acquired by binocular scanning measurement is high, and data processing is required before grid normalization is carried out so as to eliminate redundant data and facilitate normalization operation; in addition, filtering the data can eliminate errors in the data of the binocular scanning measurement, so that the data processing can be performed quickly and accurately;
the regular grid DEM data processing comprises grid normalization processing and spatial interpolation of discretized data; the grid normalization processing of the discrete data is to grid the discrete measurement point data of the plane distribution, in other words, to estimate the undetected grid point by using the measured discrete point value; because the requirement of calculating speed needs to select an optimal interpolation algorithm, the method ensures that the geographic features included in the transmission process of the digital elevation model of the inward interpolation calculation of the original data are not lost, so as to ensure the speed of interpolation; the discrete data can be expressed as a matrix after normalization processing, and in a computer, the discrete data can be expressed as a two-dimensional array, one element of each array corresponds to an elevation value, the discrete data can have the condition that the grid has no data after grid normalization, and in order to solve the condition, a reasonable spatial interpolation mode is needed to be selected for interpolation processing, and the general spatial interpolation method mainly comprises the following steps: a moving average method, a distance reciprocal square weighting method, a trend surface fitting technology, a spline method function, a nearest pixel method, a bilinear interpolation method, a three-time convolution interpolation method and the like, wherein a rapid interpolation mode is selected in consideration of calculation instantaneity and calculation amount; searching a plurality of near discrete points around each grid point according to a distance square reciprocal weighting method, and interpolating the grid point elevation one by one to establish a grid; the algorithm is easy to realize and has high speed; if other interpolation methods are adopted, a plurality of nearby measured values need to be buffered, and the method for weighting according to the square inverse distance is adopted in consideration of the special requirements of the project on real-time performance.
Step four, visualizing the processed three-dimensional data, wherein the three-dimensional data visualization comprises bulk cargo material pile surface reconstruction and material pile data three-dimensional visualization; after DEM data processing is completed, regular grid data is obtained, the regular grid is regarded as a grid image, the grid size corresponds to the image pixel size, the elevation value corresponds to the gray value, and the greatest benefit of the two technologies which are equivalent to a digital image is that the two technologies can be mutually utilized, and meanwhile, the operation time of a computer is reduced; VC++6.0 under the Windows platform is used as a development tool, openGL is adopted to draw the three-dimensional surface dynamic change condition of the stockpile in real time, and Direct3D with the strongest rendering capability under the Windows platform is selected to fully play the function of hardware acceleration.
According to the requirement, the invention can combine two visualization modes of three-dimensional contour display and bulk cargo elevation value gray level image display, and for better extracting image characteristics, an area growth method is adopted, and a specific implementation flow is shown in figure 7; firstly, selecting a known point for each area to be segmented as a seed point of a certain growth area, and merging adjacent points with similar characteristics with the seed point into the area where the seed point is located; then, the gray average value of the area is calculated, and the growth conditions are as follows: when the absolute value of the difference value between the gray average value of the region and the gray value of the adjacent point is smaller than a specified threshold value; the specific implementation method comprises the following steps: and (3) taking the seed point as a starting point, carrying out region growth in the eight-connected direction, when the adjacent points meeting the conditions meet the growth conditions, entering the region, and then repeating the process by taking the new point as the growth starting point until all the adjacent points do not meet the conditions, wherein the region generation process is terminated.
The invention has not been described in detail in the prior art, and it is apparent to those skilled in the art that the invention is not limited to the details of the above-described exemplary embodiments, but that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics thereof; the above-described embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (7)
1. A digital stockpile visualization method based on binocular vision is characterized by comprising the following steps: comprises the following steps:
S1, a three-dimensional binocular camera is adopted to establish a bulk cargo three-dimensional scanning system;
The three-dimensional binocular camera and grab buckets of the ship unloader are arranged on the trolley at intervals along the running direction of the trolley, and the running distance of the trolley and the trolley is controlled by the feedback of an absolute value encoder;
s2, bulk cargo scanning is carried out by utilizing a three-dimensional scanning system, three-dimensional data are collected, and the relative height of a bulk cargo stack is updated in real time;
The bulk scanning flow is as follows: firstly moving a cart to a starting position at one side of a bulk material pile, stopping, then controlling the cart to move and simultaneously starting a binocular camera to work, scanning one row of the bulk material pile, and completing calculation of surface structure distribution of the bulk material pile below; after a trolley scans one row to return to a starting point, calculating the distance from the trolley to the next row according to the surface reconstruction condition of the bulk material pile, moving the trolley to the next row, and scanning a next row area by the moving trolley until the surface scanning reconstruction of the whole material pile is finished;
With continuous ship unloading work, the whole ship continuously rises, so that the deck height is data changing at any time in the ship unloading process, the influence of the factor is considered, when the grab bucket takes materials back, the ship body height data can be scanned and updated in real time, and the specific scanning flow is as follows:
Performing global scanning by using a binocular camera, then calculating the deck height, if the result cannot be calculated, continuing scanning until the deck height is calculated, and then calculating the hatch position; carrying out local scanning in the ship unloading process, including trolley forward scanning and return scanning, carrying out deck height updating by single-pass scanning, updating the hatch position after updating, otherwise, continuing scanning until updating is completed;
S3, carrying out data processing on the acquired three-dimensional data; the data processing comprises bulk three-dimensional coordinate conversion, interference data removal and regular grid DEM data processing;
and S4, visualizing the processed three-dimensional data.
2. The binocular vision-based digital stockpile visualization method of claim 1, wherein the method comprises the following steps: in the line scanning path, the first position point of the grab bucket of the ship unloader corresponding to the blanking hopper, the second position point and the third position point of the binocular camera corresponding to the edges of the two ends of the bulk cargo material pile, and the fourth position point and the fifth position point of the grab bucket of the ship unloader corresponding to the edges of the two ends of the bulk cargo material pile are included.
3. The binocular vision-based digital stockpile visualization method of claim 1, wherein the method comprises the following steps: in S2, the binocular camera data acquisition is to perform preliminary analysis and data reliability test on bulk cargo stacking surface data acquired by the acquisition, so as to analyze the verified data according to the format data of the protocol, thereby acquiring binocular camera measurement data in the form of polar coordinate expression.
4. The binocular vision-based digital stockpile visualization method of claim 1, wherein the method comprises the following steps: in S3, the interference data removal means to eliminate redundant data and error data.
5. The binocular vision-based digital stockpile visualization method of claim 1, wherein the method comprises the following steps: in S3, the three-dimensional coordinate transformation is to use the cart row to make the initial position as the origin of coordinates, use the cart travelling direction as the y axis, use the cart travelling direction as the x axis to establish a bulk cargo material pile coordinate system o-xyz, set the B point coordinate as (x, y, z) under the binocular camera coordinate system, as (u, v, w) under the bulk cargo material pile system, and the binocular camera origin as (u 0, v0, w 0) under the bulk cargo material pile coordinate system, so as to obtain the transformation relation (u, v, w) = (x, y, z) + (u 0, v0, w 0) from the binocular camera coordinate system to the bulk cargo material pile coordinate system; wherein u0, v0, w0 can be calculated by the positions of the cart and the trolley in the bulk material pile coordinate system; thereby converting the coordinates output by the binocular camera into three-dimensional coordinates of bulk cargo in a bulk cargo stack coordinate system.
6. The binocular vision-based digital stockpile visualization method of claim 1, wherein the method comprises the following steps: in S3, the regular grid DEM data processing includes grid normalization processing and spatial interpolation of discretized data.
7. The binocular vision-based digital stockpile visualization method of claim 1, wherein the method comprises the following steps: in S4, the visualization of the three-dimensional data comprises bulk material pile surface reconstruction and three-dimensional visualization of pile data; after DEM data processing is completed, regular grid data is obtained, the regular grid is regarded as a grid image, the grid size corresponds to the pixel size of the image, and the elevation value corresponds to the gray value, so that the grid image is equivalent to the digital image; the visual component adopts VC++6.0 as a development tool under the Windows platform, adopts OpenGL to draw the dynamic change condition of the three-dimensional surface of the stockpile in real time, and simultaneously selects Direct3D under the Windows platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311769054.XA CN117437291B (en) | 2023-12-21 | 2023-12-21 | Digital stockpile visualization method based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311769054.XA CN117437291B (en) | 2023-12-21 | 2023-12-21 | Digital stockpile visualization method based on binocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117437291A CN117437291A (en) | 2024-01-23 |
| CN117437291B true CN117437291B (en) | 2024-05-17 |
Family
ID=89548394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311769054.XA Active CN117437291B (en) | 2023-12-21 | 2023-12-21 | Digital stockpile visualization method based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117437291B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334897A (en) * | 2007-06-27 | 2008-12-31 | 宝山钢铁股份有限公司 | Three-dimensional imaging method for implementing material pile real time dynamic tracking |
| WO2018103693A1 (en) * | 2016-12-07 | 2018-06-14 | 西安知象光电科技有限公司 | Hybrid light measurement method for measuring three-dimensional profile |
| CN109816778A (en) * | 2019-01-25 | 2019-05-28 | 北京百度网讯科技有限公司 | Material heap three-dimensional rebuilding method, device, electronic equipment and computer-readable medium |
| WO2021098079A1 (en) * | 2019-11-21 | 2021-05-27 | 大连理工大学 | Method for using binocular stereo camera to construct grid map |
| CN116222425A (en) * | 2023-02-16 | 2023-06-06 | 北京航达青云科技有限公司 | Three-dimensional reconstruction method and system based on multi-view three-dimensional scanning device |
| CN117058211A (en) * | 2022-05-05 | 2023-11-14 | 上海宝信软件股份有限公司 | Grab bucket anti-shake collision strategy control method and system based on laser positioning |
-
2023
- 2023-12-21 CN CN202311769054.XA patent/CN117437291B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334897A (en) * | 2007-06-27 | 2008-12-31 | 宝山钢铁股份有限公司 | Three-dimensional imaging method for implementing material pile real time dynamic tracking |
| WO2018103693A1 (en) * | 2016-12-07 | 2018-06-14 | 西安知象光电科技有限公司 | Hybrid light measurement method for measuring three-dimensional profile |
| CN109816778A (en) * | 2019-01-25 | 2019-05-28 | 北京百度网讯科技有限公司 | Material heap three-dimensional rebuilding method, device, electronic equipment and computer-readable medium |
| WO2021098079A1 (en) * | 2019-11-21 | 2021-05-27 | 大连理工大学 | Method for using binocular stereo camera to construct grid map |
| CN117058211A (en) * | 2022-05-05 | 2023-11-14 | 上海宝信软件股份有限公司 | Grab bucket anti-shake collision strategy control method and system based on laser positioning |
| CN116222425A (en) * | 2023-02-16 | 2023-06-06 | 北京航达青云科技有限公司 | Three-dimensional reconstruction method and system based on multi-view three-dimensional scanning device |
Non-Patent Citations (3)
| Title |
|---|
| An automatic warehouse clearance scheme for bulk cargo unloading in ports;Pulin Li等;2022 2nd Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS);20221231;296-299 * |
| 基于双目视觉的智能化抓斗卸船机关键技术研究;陆成浩;中国优秀硕士学位论文全文数据库工程科技Ⅱ辑;20210815(第08期);C034-367 * |
| 自动抓斗卸船三维激光扫描系统的应用;何琼等;武汉职业技术学院学报;20111031;第10卷(第5期);1-4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117437291A (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110969624B (en) | Laser radar three-dimensional point cloud segmentation method | |
| Kim et al. | SLAM-driven robotic mapping and registration of 3D point clouds | |
| CN109029254B (en) | Train carriage cargo volume and bulk density quality detection method based on point cloud data processing | |
| CN106709947B (en) | Three-dimensional human body rapid modeling system based on RGBD camera | |
| CN110194375B (en) | Automatic stacking, taking and stacking method and system for material yard | |
| CN110230998B (en) | Rapid and precise three-dimensional measurement method and device based on line laser and binocular camera | |
| CN111476242B (en) | Laser point cloud semantic segmentation method and device | |
| CN115236628B (en) | Method for detecting residual cargoes in carriage based on laser radar | |
| CN105160702A (en) | Stereoscopic image dense matching method and system based on LiDAR point cloud assistance | |
| CN111192328B (en) | Carriage container three-dimensional scanning system point cloud processing method based on two-dimensional laser radar | |
| CN114419130A (en) | Bulk cargo volume measurement method based on image characteristics and three-dimensional point cloud technology | |
| CN111899328A (en) | Point cloud three-dimensional reconstruction method based on RGB data and generation countermeasure network | |
| CN112833784B (en) | Steel rail positioning method combining monocular camera with laser scanning | |
| CN112017248B (en) | 2D laser radar camera multi-frame single-step calibration method based on dotted line characteristics | |
| Borsu et al. | Automated surface deformations detection and marking on automotive body panels | |
| WO2023142608A1 (en) | System and method for obtaining aircraft profile | |
| US20230267593A1 (en) | Workpiece measurement method, workpiece measurement system, and program | |
| CN111860321A (en) | Obstacle identification method and system | |
| CN114612632A (en) | Sorting and interpolation processing method based on three-dimensional laser point cloud data | |
| CN115423958A (en) | Mining area travelable area boundary updating method based on visual three-dimensional reconstruction | |
| CN112525106B (en) | Three-phase machine cooperative laser-based 3D detection method and device | |
| CN113819844A (en) | Method, device and equipment for identifying traveling materials and readable storage medium | |
| CN117437291B (en) | Digital stockpile visualization method based on binocular vision | |
| CN112164044A (en) | Wear analysis method of rigid contact net based on binocular vision | |
| CN110310371B (en) | Method for constructing three-dimensional contour of object based on vehicle-mounted monocular focusing sequence image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |